EP2908267B1 - Image processing device and image processing method - Google Patents
Image processing device and image processing method Download PDFInfo
- Publication number
- EP2908267B1 EP2908267B1 EP14196764.6A EP14196764A EP2908267B1 EP 2908267 B1 EP2908267 B1 EP 2908267B1 EP 14196764 A EP14196764 A EP 14196764A EP 2908267 B1 EP2908267 B1 EP 2908267B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- region
- joint
- candidate
- finger
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Not-in-force
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/235—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on user input or interaction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/11—Hand-related biometrics; Hand pose recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
Definitions
- the embodiment discussed herein is related to, for example, an image processing device, image processing method, and image processing program used to detect a finger of a user.
- AR augmented reality
- the position of a finger of the user has to be located accurately by using a camera fixed to an arbitrary position or a camera which is freely movable.
- a method to locate the position of a finger for example, a technology has been disclosed to extract a contour of a hand by extracting a color component (may be referred to as color feature amount) of the flesh color from an imaged image and to locate the position of the finger from the contour.
- a technology of image processing as described above for example, non-patent documents such as " Survey on Skin Tone Detection using Color Spaces, C. Prema et al., International Journal of Applied Information Systems 2(2):18-26, May 2012.
- An object of the present disclosure is to provide an image processing device which makes it possible to locate the position of a finger of the user accurately without being influenced by the background color.
- an image processing device according to claim 1 is presented.
- FIG. 1 is a functional block diagram of an image processing device 1 according to an embodiment.
- the image processing device 1 includes an acquisition unit 2, extraction unit 3, detection unit 4, determination unit 5, and selection unit 6.
- the image processing device 1 also includes a not-illustrated communication unit, and may use network resources by transmitting and receiving data bi-directionally to and from various external devices via a communication channel.
- the acquisition unit 2 for example, is a hardware circuit configured with a wired logic.
- the acquisition unit 2 may also be a function module implemented by a computer program executed on the image processing device 1.
- the acquisition unit 2 receives an image imaged by an external device.
- the external device imaging the image is, for example, an image sensor.
- the image sensor is, for example, an imaging device such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) camera.
- CCD charge coupled device
- CMOS complementary metal oxide semiconductor
- the acquisition unit 2 may convert the analog image into a digital image through sampling, by which analog signals are extracted at discrete positions, and then quantization, by which the analog signals are converted to numerical values with finite resolution.
- the acquisition unit 2 may also acquire the image by, for example, issuing instructions of imaging with an interval of 30 fps to the image sensor.
- the image sensor may be used as a head mounted camera (HMC).
- the image sensor for example, images an image including a first region and second region of a user.
- the image sensor may also be included in the image processing device 1 as appropriate.
- the first example will be described, for the purpose of illustration, on the assumption that the first region is a region including the dorsum of hand (may be referred to as the back of the hand) and a portion from the second joint to the third joint of a finger, and the second region is a region located in the direction from the second joint to the fingertip of a finger.
- regions located in the direction from the second joint to the fingertip of a finger include, for example, a region from the fingertip to the second joint, a region from the first joint to the second joint, and a region from the fingertip to the first joint.
- the first example will also be described, for the purpose of illustration, on the assumption that the dorsum of hand and a finger are in a state of facing the image sensor (in other words, in a state of being opposite to the image sensor), and, a finger (for example, index finger) is in a state of being spread to carry out interaction operation.
- the acquisition unit 2 outputs the acquired image to the extraction unit 3.
- the extraction unit 3 for example, is a hardware circuit configured with a wired logic.
- the extraction unit 3 may also be a function module implemented by a computer program executed on the image processing device 1.
- the extraction unit 3 receives the image from the acquisition unit 2.
- the extraction unit 3 may, from the viewpoint of processing load reduction, distinguish flesh-colored areas from non-flesh-colored areas in the image, and exclude the non-flesh-colored areas from a series of image processing targets.
- the first example for the purpose of illustration, will be described on the assumption that the extraction unit 3 distinguishes flesh-colored areas from non-flesh-colored areas in the image, and excludes the non-flesh-colored areas from a series of image processing targets.
- a flesh-colored area may be determined on any color space such as RGB, HSV, and YCbCr.
- the methods to distinguish a flesh-colored area include a method to determine a flesh-colored area based on whether or not the pixel value of each color component of RGB (may be referred to as color feature quantity) is within an arbitrary range (for example, 100 ⁇ R ⁇ 255, 0 ⁇ G ⁇ 70, and 0 ⁇ B ⁇ 70), a method to determine a flesh-colored area by every pixel value (for example, when pixel values are (R1, G1, B1), the pixel is decided to be in a flesh-colored area, and, when pixel values are (R2, G2, B2), the pixel is decided to be in a non-flesh-colored area), and so on.
- the RGB, HSV, and YCbCr color spaces may be interconverted with one another, and it thus becomes possible to determine a flesh-colored area on other color spaces in the same manner as on the above-de
- the extraction unit 3 receives the image from the acquisition unit 2 and extracts a group of candidate areas for the first region and second region of a user included in the image based on pixel values in the image.
- the extraction unit 3 for example, extracts a group of candidate areas based on a predetermined first pixel value which is determined based on differences between pixel values of adjacent pixels in the image and by which the first region and second region are extracted separately.
- the extraction unit 3 separates pixels included in the flesh-colored area into a plurality of areas (a group of candidate areas for the first region and second region).
- the extraction unit 3 may, for example, extract a group of candidate areas by using differences between pixel values of adjacent pixels in the flesh-colored area.
- D_ab a difference between the pixel values (may be referred to as distance) D_ab may be expressed by the following formula.
- D _ ab sqrt Ra ⁇ Rb 2 + Ga ⁇ Gb 2 + Ba ⁇ Bb 2
- the extraction unit 3 when the difference between pixel values D_ab is less than a predetermined first pixel value (for example, a first pixel value of 5) in the above (formula 1), extracts the areas as candidate areas in an identical group, and, when the difference between pixel values D_ab is equal to or greater than the threshold value, extracts the areas as candidate areas in different groups.
- a predetermined first pixel value for example, a first pixel value of 5
- FIG. 2A illustrates an example of an image which the acquisition unit 2 acquires.
- FIG. 2B illustrates an example of a flesh-colored area which the extraction unit 3 extracts from the image.
- FIG. 2C illustrates an example of a group of candidate areas for the first region and second region which the extraction unit 3 extracts based on differences between pixel values of adjacent pixels in the flesh-colored area.
- the image which the acquisition unit 2 acquires includes the first region and second region of a user which overlap a plane of paper including information such as a photograph and the flesh-colored background. As illustrated in FIG.
- the extraction unit 3 may, by using the method disclosed above, extract the flesh-colored area included in the image.
- the first region and second region of the user and the background area of the plane of paper are extracted as a flesh-colored area.
- the first region is extracted as a candidate area in a group
- the second region is extracted as a plurality of candidate areas in a state of being separated into a plurality of groups.
- the background area of the plane of paper is also extracted as candidate areas in a state of being separated into a plurality of groups. This is because pixel values of the plane of paper, for example, vary under the influence of surface reflection of light.
- the first pixel value may be any pixel value by which the first region, second region, and background area are extracted separately.
- the idea of the first pixel value is an idea which is newly revealed through consistent study by the applicants and has not been previously disclosed. In an image including the dorsum of hand and a finger, because regions including wrinkles of skin existing on the first joint and second joint of a finger or nails have complex shapes, differences between pixel values of adjacent pixels have pixel values peculiar to the regions.
- the extraction unit 3 may determine a predetermined second pixel value (for example, a second pixel value of 7), which makes it possible to separate the first region from the second region, in advance.
- a predetermined second pixel value for example, a second pixel value of 7
- the extraction unit 3 may determine a predetermined third pixel value (for example, a third pixel value of 5), which makes it possible to separate the first region and second region from the background area, in advance.
- the first pixel value may be determined by a process in which the second pixel value and the third pixel value are compared, and the smaller one (the value which makes it possible both to separate the first region from the second region and to separate the first region and second region from the background area) is determined as the first pixel value.
- the extraction unit 3 may extract a group of candidate areas for the first region and second region from the areas corresponding to the first region and second region and the area other than the areas corresponding to the first region and second region (background area).
- the extraction unit 3 may extract the group of candidate areas for the first region and second region based on, for example, an edge extraction method disclosed in " N. Senthilkumaran et al., Edge Detection Techniques for Image Segmentation, A Survey of Soft Computing Approaches, International Journal of Recent Trends in Engineering, Vol. 1, No. 2, May 2009 ".
- the extraction unit 3 outputs the extracted group of candidate areas to the detection unit 4 and selection unit 6.
- the detection unit 4 illustrated in FIG. 1 is, for example, a hardware circuit configured with a wired logic.
- the detection unit 4 may also be a function module implemented by a computer program executed on the image processing device 1.
- the detection unit 4 receives the group of candidate areas from the extraction unit 3.
- the detection unit 4 detects a candidate area corresponding to the first region from the group of candidate areas based on biometric characteristics of the first region.
- the biometric characteristics for example, may include at least one of the area, shape, and statistic of pixel values of the first region.
- the detection unit 4 outputs the detected candidate area for the first region to the determination unit 5. Details of detection processing in the detection unit 4 with respect to each biometric characteristic of the first region will be described below.
- the detection unit 4, however, may detect a candidate area corresponding to the first region by combining individual biometric characteristics in order to improve robustness.
- the detection unit 4 detects the candidate area corresponding to the first region based on the area of the first region, which is an example of biometric characteristics.
- Sn the area of each candidate area in the group of candidate areas received from the extraction unit 3
- the detection unit 4 may detect the candidate area corresponding to the first region based on the following formula. TH 01 ⁇ Sn ⁇ TH 02
- TH01 and TH02 denote arbitrary threshold values, which may be determined by measuring in advance a typical first region of a single user or a plurality of users who use(s) the image processing device 1. For example, when it is assumed that the size of an image the acquisition unit 2 acquires is 76800 pixels (320 pixels ⁇ 240 pixels), and the distance between the image sensor and the first region is 50 cm, TH01 and TH02 may be determined to have values of 2000 pixels and 10000 pixels, respectively.
- the detection unit 4 may detect a candidate area that has the area value closest to the mean value of TH01 and TH02 as the candidate area corresponding to the first region.
- the detection unit 4 detects a candidate area corresponding to the first region based on the shape of the first region, which is an example of biometric characteristics.
- the detection unit 4 may detect the candidate area corresponding to the first region by carrying out any type of template matching between the outer edges of each candidate area in the group of candidate areas and, for example, the outer edges of a pre-measured first region(s) of a single user or a plurality of users.
- the detection unit 4 may also detect the candidate area corresponding to the first region by detecting parallel line segments of the outer edges of candidate areas in the group of candidate areas (because the width of a finger is substantially invariable, the outer edges at the left end and the right end of the finger constitute parallel line segments) and selecting a candidate area the detected parallel line segments of which are shorter than or equal to a predetermined threshold value (the threshold value may be appropriately defined based on the length from the second joint to the third joint of a finger).
- the detection unit 4 may use, as the method to detect parallel line segments, a method disclosed in, for example, " Zheng et.
- the detection unit 4 may detect a candidate area which has a highest degree of similarity to the template or a candidate area the parallel line segment length of which is closest to the predetermined threshold value as the candidate area corresponding to the first region.
- the detection unit 4 detects the candidate area corresponding to the first region based on a statistic of pixel values of the first region, which is an example of biometric characteristics.
- the detection unit 4 may detect the candidate area corresponding to the first region by using the average pixel value (Ar, Ag, Ab) and standard deviation ( ⁇ r, ⁇ g, ⁇ b) (for example, on the RGB color space) of each candidate area in the group of candidate areas received from the extraction unit 3, based on the following formulae.
- TH03 to TH14 denote arbitrary threshold values which may be determined by measuring a typical first region of a single user or a plurality of users who use(s) the image processing device 1, in advance.
- the dorsum of hand and the area from the second joint to the third joint include minuscule portions with slightly different colors (may be referred to as color characteristic quantity), such as a slightly reddish portion, a slightly whitish portion, and a slightly blackish portion (above a blood vessel or the like).
- color characteristic quantity may be referred to as color characteristic quantity
- the standard deviation of pixel values in the dorsum of hand and the area from the second joint to the third joint is larger than those on the plane of paper with a single color of the flesh color, which is an example of the background. It is possible for the detection unit 4 to use variance in place of standard deviation.
- the detection unit 4 may detect a candidate area the average pixel value of which is closest to the mean value of TH03 and TH04 or TH09 and TH10 as the candidate area corresponding to the first region.
- FIG. 3 illustrates an example of the candidate area corresponding to the first region which the detection unit 4 detects.
- the detection unit 4 detects the candidate area corresponding to the first region from the group of candidate areas illustrated in FIG. 2C based on biometric characteristics of the first region.
- the detection unit 4 outputs the detected candidate area corresponding to the first region to the determination unit 5.
- the determination unit 5 illustrated in FIG. 1 is, for example, a hardware circuit configured with a wired logic.
- the determination unit 5 may be a function module implemented by a computer program executed on the image processing device 1.
- the determination unit 5 receives, from the detection unit 4, the candidate area corresponding to the first region detected by the detection unit 4.
- the determination unit 5 determines a connection direction between the first region and the second region based on the outer edges of the candidate area for the first region.
- the determination unit 5 detects outer edges from the candidate area corresponding to the first region.
- the determination unit 5 may use various well-known methods as a method to detect outer edges.
- the determination unit 5 may use, as a method to detect outer edges, a method disclosed in, for example, " Song et. al., A Hough transform based line recognition method utilizing both parameter space and image space, Pattern Recognition, 38, 2005, p.539 - p.552 ".
- the determination unit 5 detects parallel line segments from the detected outer edges.
- the parallel line segments for example, correspond to the outer edges of the portion from the second joint to the third joint of the finger (because the width of a finger is substantially invariable, the outer edges at the left end and right end of the finger constitute parallel line segments).
- the determination unit 5 may use, as a method to detect parallel line segments, a method disclosed in, for example, " Zheng et. al., A Parallel-Line Detection Algorithm Based on HMM Decoding, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 5, MAY 2005 " or " Niinuma et. al., Detecting Shading Regions based on the Contour Representation of an Image, The Special Interest Group Technical Reports of IPSJ, 2001, 36, p1-8 ".
- the width of a finger is substantially invariable, the outer edges of the finger are not parallel in a precise sense.
- the determination unit 5 may use any threshold decision method in detection of parallel line segments.
- the threshold value may be determined by measuring an angle made by the outer edges at the left end and right end of a typical finger of a single user or a plurality of users who use(s) the image processing device 1. For example, the determination unit 5 may decide that two line segments are parallel line segments if the angle made by the two line segments is less than 5°. In this case, the determination unit 5 may define completely parallel line segments by correcting the gradient of each of two line segments decided to be parallel with, for example, the quotient of the angle made by the two line segments divided by 2.
- the determination unit 5 may regard the longest parallel line segments as the finger by which the user is carrying out interactive operation.
- FIG. 4 illustrates an example of a connection direction which the determination unit 5 determines.
- the determination unit 5 determines parallel line segments from the outer edges and further determines the connection direction from the parallel line segments. It is sufficient for the connection direction to be, for example, parallel with the parallel line segments.
- the determination unit 5 outputs the determined connection direction between the first region and second region to the selection unit 6.
- the selection unit 6 illustrated in FIG. 1 is a hardware circuit configured with a wired logic.
- the selection unit 6 may be a function module implemented by a computer program executed on the image processing device 1.
- the selection unit 6 receives the connection direction from the determination unit 5 and the group of candidate areas from the extraction unit 3.
- the selection unit 6 selects candidate areas corresponding to the second region based on the connection direction from the group of candidate areas excluding the candidate area corresponding to the first region.
- the selection unit 6 for example, selects candidate areas corresponding to the second region further based on the areas of the group of candidate areas or pixel values of the first region and the group of candidate areas. Details of the selection processing by the selection unit 6 will be described below.
- the selection unit 6 may, however, detect candidate areas corresponding to the second region by combining selection processing methods in order to improve robustness.
- FIG. 5A is a diagram illustrating the candidate area corresponding to the first region and the connection direction thereof and a group of candidate areas for the second region.
- FIG. 5B is a diagram illustrating the candidate area corresponding to the first region detected by the detection unit 4 and the candidate areas corresponding to the second region selected by the selection unit 6.
- the connection direction between the first region and the second region may be referred to as an extension line of the median line of parallel line segments
- the parallel line segments, and extension lines of the parallel line segments are illustrated.
- the selection unit 6, for example, selects candidate areas existing in the connection direction as candidate areas corresponding to the second region.
- the selection unit 6, for example may also select candidate areas corresponding to the second region based on areas between the extension lines of the parallel line segments.
- This selection processing uses a biometric characteristic in that outer edges of regions from the fingertip to the first joint to the second joint to the third joint (outer edges of a finger) constitute substantially straight lines.
- the selection unit 6 illustrated in FIG. 1 may select candidate areas corresponding to the second region based on, for example, a distance B_distance (the unit may, for example, be the number of pixels) between extension lines of the parallel line segments and outer edges of the group of candidate areas (for example, distance between the extension line of the median line of the parallel line segments and a point on the outer edges that is furthest from the extension line of the median line of the parallel line segments).
- the selection unit 6 may, for example, select candidate areas that satisfy a condition expressed by the following formula as the candidate areas corresponding to the second region.
- TH15 is an arbitrary threshold value which is determined by measuring in advance a typical second region of a single user or a plurality of users who use(s) the image processing device 1.
- TH15 may be 10.
- the selection unit 6 may, for example, select candidate areas corresponding to the second region based on an area B_area (the unit may, for example, be the number of pixels) of a candidate area in the group of candidate areas.
- the selection unit 6 may, for example, select a candidate area that satisfies a condition expressed by the following formula as a candidate area corresponding to the second region. TH 16 ⁇ B _ area ⁇ TH 17
- TH16 and TH17 are arbitrary threshold values which are determined by measuring in advance a typical second region of a single user or a plurality of users who use(s) the image processing device 1.
- TH16 and TH17 may be 2 and 300, respectively.
- TH16 may be determined based on the area of minuscule areas produced by shade of light.
- the selection unit 6 may, for example, select a candidate area corresponding to the second region based on an average value B_ave and standard deviation ⁇ _ ⁇ of pixel values of each candidate area in the group of candidate areas and an average value A_ave and standard deviation A_ ⁇ of pixel values of the candidate area corresponding to the first region.
- the selection unit 6 may, for example, select a candidate area that satisfies a condition expressed by the following formula as a candidate area corresponding to the second region.
- TH18 and TH19 are arbitrary threshold values which are determined by measuring a typical first region and second region of a single user or a plurality of users who use(s) the image processing device 1 in advance.
- TH18 and TH19 may be 20 and 5, respectively.
- TH18 and TH19 may be determined based on a biometric characteristic in that pigments of adjacent skin areas resemble each other.
- the image processing device 1 may regard a concatenation of the candidate area corresponding to the first region detected by the detection unit 4 and the candidate areas corresponding to the second region selected by the selection unit 6 as a finger of the user, and detect a position of the fingertip from the outer edge (contour) of the finger by an arbitrary method.
- the image processing device 1 may use, as a method to detect a position of the fingertip, a method disclosed in, for example, " Survey on Skin Tone Detection using Color Spaces, C. Prema et al., International Journal of Applied Information Systems 2(2): 18-26, May 2012. Published by Foundation of Computer Science, New York, USA .”.
- the image processing device 1 outputs the detected position of the fingertip to an external device (for example, an information processing terminal device or the like).
- the image processing device 1 may, for example, be configured with integrated circuits such as an application specific integrated circuit (ASIC) and field programmable gate array (FPGA).
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- FIG. 6 is a flowchart of the image processing carried out by the image processing device 1.
- the acquisition unit 2 receives, from the image sensor, an image imaged by the image sensor which includes at least the first region and second region of a user (step S601).
- the acquisition unit 2 may convert the analog image into a digital image through sampling, by which analog signals are extracted at discrete positions, and then quantization, by which the analog signals are converted to numerical values with finite resolution.
- the acquisition unit 2 may also acquire the image by, for example, issuing instructions of imaging with an interval of 30 fps to the image sensor.
- the acquisition unit 2 outputs the acquired image to the extraction unit 3.
- the extraction unit 3 receives the image from the acquisition unit 2, and extracts a group of candidate areas for the first region and second region of the user included in the image based on pixel values in the image (step S602).
- the extraction unit 3 for example, extracts a group of candidate areas based on a predetermined first pixel value which is determined based on differences between pixel values of adjacent pixels in the image and by which the first region and the second region are extracted separately.
- the extraction unit 3 separates pixels included in a flesh-colored area into a plurality of areas (a group of candidate areas for the first region and second region).
- the extraction unit 3 for example, extracts the group of candidate areas by using differences between pixel values of adjacent pixels in the flesh-colored area and the above-described processing method of the extraction unit 3.
- the acquisition unit 2 may acquire an image at a different moment (for example, the next frame) (step S601), and the extraction unit 3 may carry out the processing in step S602 again.
- the extraction unit 3 may, from the viewpoint of processing load reduction, distinguish flesh-colored areas from non-flesh-colored areas in the image by using the above-described processing method of the extraction unit 3, and exclude the non-flesh-colored areas from a series of image processing targets.
- the extraction unit 3 distinguishes the flesh-colored area from the non-flesh-colored areas in the image and excludes the non-flesh-colored areas from a series of image processing targets.
- the extraction unit 3 outputs the extracted group of candidate areas to the detection unit 4 and selection unit 6.
- the detection unit 4 receives the group of candidate areas from the extraction unit 3.
- the detection unit 4 by using the above-described processing method of the detection unit 4, detects the candidate area corresponding to the first region from the group of candidate areas based on biometric characteristics of the first region (step S603).
- the biometric characteristics may, for example, include at least one of the area, the shape, and a statistic of pixel values of the first region.
- the detection unit 4 outputs the detected candidate area for the first region to the determination unit 5.
- the determination unit 5 receives, from the detection unit 4, the candidate area corresponding to the first region detected by the detection unit 4.
- the determination unit 5 based on the outer edges of the candidate area for the first region, determines the connection direction between the first region and the second region by using the above-described processing method of the determination unit 5 (S604).
- step S602 when the determination unit 5 detects a plurality of parallel line segments (in other words, when parallel line segments of portions from the second joints to the third joints of the thumb and the index finger are detected), for example, the determination unit 5 may regard the longest parallel line segments as the finger by which the user is carrying out interactive operation.
- the determination unit 5 outputs the determined connection direction between the first region and the second region to the selection unit 6.
- the selection unit 6 receives the connection direction from the determination unit 5 and the group of candidate areas from the extraction unit 3.
- the selection unit 6, based on the connection direction, selects candidate areas corresponding to the second region from the group of candidate areas excluding the candidate area corresponding to the first region by using the above-described processing method of the selection unit 6 (step S605).
- the selection unit 6, for example, selects candidate areas corresponding to the second region based on distances between the extension line of the median line of the parallel line segments and the outer edges of the group of candidate areas or areas between extension lines of the parallel line segments.
- the selection unit 6, for example, selects candidate areas corresponding to the second region further based on the area of the group of candidate areas or pixel values of the first region and the group of candidate areas.
- the selection unit 6 may, in order to improve robustness, detect a candidate area corresponding to the second region by combining the above-described selection processing methods.
- the image processing device 1 (for example, the selection unit 6) regards a concatenation of the candidate area corresponding to the first region detected by the detection unit 4 and the candidate areas corresponding to the second region selected by the selection unit 6 as a finger of the user, and detects a position of the fingertip from the outer edge (contour) of the finger by an arbitrary method (step S606). With this processing, the image processing device 1 ends the image processing illustrated in the flowchart of FIG. 6 .
- the image processing device of the example 1 it becomes possible to locate a position of a finger of a user accurately without being influenced by a background color.
- a hand is flesh-colored
- the background is also flesh-colored, and the processing methods for these portions are similar
- embodiments are not limited to this case.
- the embodiment described in the example 1 is also applicable to a case in which fingers are covered by a glove and a background with a similar color to the color of the glove is used.
- FIG. 7 is a hardware configuration diagram of a computer which functions as an image processing device 1 according to an embodiment. As illustrated in FIG. 7 , the image processing device 1 is configured with a computer 100 and input/output devices (peripheral devices) connected to the computer 100.
- input/output devices peripheral devices
- the whole computer 100 is controlled by a processor 101.
- a processor 101 To the processor 101, a random access memory (RAM) 102 and a plurality of peripheral devices are connected via a bus 109.
- the processor 101 may be a multiprocessor.
- the processor 101 is, for example, a CPU, micro processing unit (MPU), digital signal processor (DSP), application specific integrated circuit (ASIC), or programmable logic device (PLD).
- the processor 101 may be a combination of two or more components among a CPU, MPU, DSP, ASIC, and PLD.
- the processor 101 may, for example, carry out processing of function blocks such as an acquisition unit 2, extraction unit 3, detection unit 4, determination unit 5, and selection unit 6 in FIG. 1 .
- the RAM 102 is used as a main memory of the computer 100. To the RAM 102, at least a portion of operating system (OS) programs and application programs, which are executed by the processor 101, are stored temporarily. To the RAM 102, various kinds of data, which is used in processing executed by the processor 101, are also stored.
- OS operating system
- application programs which are executed by the processor 101.
- Peripheral devices connected to the bus 109 include a hard disk drive (HDD) 103, graphic processor unit 104, input interface 105, optical drive unit 106, device connection interface 107, and network interface 108.
- HDD hard disk drive
- the HDD 103 carries out data writing and reading magnetically to and from an internal disk.
- the HDD 103 for example, is used as an auxiliary storage device for the computer 100.
- OS programs, application programs, and various kinds of data are stored.
- Semiconductor memory devices such as a flash memory may also be used as an auxiliary storage device.
- a monitor 110 is connected to the graphic processing device 104.
- the graphic processing device 104 following instructions from the processor 101, makes the monitor 110 display various images on a display thereof.
- a display device using a cathode ray tube (CRT) and a liquid crystal display device may be used for the monitor 110.
- a keyboard 111 and a mouse 112 are connected to the input interface 105.
- the input interface 105 transmits signals transmitted from the keyboard 111 and mouse 112 to the processor 101.
- the mouse 112 is just an example of a pointing device. Other types of pointing devices may be used.
- the other types of pointing devices include a touch panel, tablet, touch pad, trackball and the like.
- the optical drive unit 106 reads out data recorded in the optical disk 113 by using a laser beam or the like.
- the optical disk 113 is a portable recording medium on which data are recorded so as to be readable by the reflection of light.
- the optical disk 113 includes a digital versatile disc (DVD), DVD-RAM, compact disc read only memory (CD-ROM), compact disc-recordable (CD-R), compact disc-rewritable (CD-RW), or the like.
- Programs stored in the optical disk 113, which is a portable recording medium, are installed in the image processing device 1 via the optical drive unit 106.
- the installed pre-arranged programs become executable on the image processing device 1.
- the device connection interface 107 is a communication interface to connect peripheral devices to the computer 100.
- a memory device 114, memory reader/writer 115, and image sensor 118 may be connected to the device connection interface 107.
- the memory device is a recording medium equipped with a communication function with the device connection interface 107.
- the memory reader/writer 115 is a device configured to write data to a memory card 116, or to read out data from the memory card 116.
- the memory card 116 is a card-type recording medium.
- the image sensor 118 is, for example, an imaging device such as a charge coupled device (CCD) and complementary metal oxide semiconductor (CMOS) camera. The image sensor 118, for example, images an image including the first region and second region of a user.
- CCD charge coupled device
- CMOS complementary metal oxide semiconductor
- the network interface 108 is connected to a network 117.
- the network interface 108 transmits and receives data to and from another computer or communication device via the network 117.
- the computer 100 accomplishes the above-described image processing function by executing programs recorded in a computer-readable recording medium.
- the programs describing processing details executed by the computer 100 may be recorded in various recording media.
- the above-described programs may be configured with one or a plurality of function modules.
- the programs may be configured with function modules that accomplish the processing of the acquisition unit 2, extraction unit 3, detection unit 4, determination unit 5, and selection unit 6 illustrated in FIG. 1 .
- the programs executed by the computer 100 may be stored in the HDD 103.
- the processor 101 loads at least a portion of the programs stored in the HDD 103 into the RAM 102 and executes the programs.
- the programs executed by the computer 100 may also be recorded in a portable recording medium such as the optical disk 113, memory device 114, and memory card 116.
- the programs stored in a portable recording medium are installed in the HDD 103 under the control of the processor 101, and then become executable.
- the processor 101 may directly read out the programs from the portable recording medium and execute the programs.
Description
- The embodiment discussed herein is related to, for example, an image processing device, image processing method, and image processing program used to detect a finger of a user.
- In recent years, a technology has been developed to realize user operation support by, for example, making a user carry out interaction operation toward a projection image which is, by using a paper document and a projector, projected on the paper document. For example, an augmented reality (AR) technology has been disclosed in which, when a user points to a word on a paper document by his/her finger, a projection image associated with the word is projected, and, when the user further points to a portion of the projection image, notes or the like associated with the word are displayed.
- In the above described interface, the position of a finger of the user has to be located accurately by using a camera fixed to an arbitrary position or a camera which is freely movable. As a method to locate the position of a finger, for example, a technology has been disclosed to extract a contour of a hand by extracting a color component (may be referred to as color feature amount) of the flesh color from an imaged image and to locate the position of the finger from the contour. As a technology of image processing as described above, for example, non-patent documents such as "Survey on Skin Tone Detection using Color Spaces, C. Prema et al., International Journal of Applied Information Systems 2(2):18-26, May 2012. Published by Foundation of Computer Science, New York, USA.", "Skin Detection - a Short Tutorial, Elgammal et al., Encyclopedia of Biometrics by Springer-Verlag Berlin Heidelberg 2009.", "A survey of skin-color modeling and detection methods, Kakumanu et al., Pattern Recognition, Volume 40, ", Ender Konukoglu et al: "Shape-Based Hand Recognition", Proceedings of IEEE-SIU 2004, IEEE 12th Signal Processing and Telecommunication Applications Conference, 28 April 2004 "A Survey on Pixel-Based Skin Color Detection Techniques, Vezhnevets et al., IN PROC. GRAPHICON-2003." have been disclosed.
- However, in the technology in which the position of a finger of the user is located by using color feature amount, when the color of the background of a plane of paper or the like onto which an projection image is projected is the flesh color, flesh-colored components of the finger and flesh-colored components of the background become un-separable. Thus, it is difficult to locate the position of the finger. An object of the present disclosure is to provide an image processing device which makes it possible to locate the position of a finger of the user accurately without being influenced by the background color.
- In the present invention, an image processing device according to
claim 1 is presented. - The object and advantages of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, as claimed.
- With an image processing device disclosed in the present disclosure, it becomes possible to locate the position of a finger of a user accurately without being influenced by a background color.
- These and/or other aspects and advantages will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawing of which:
-
FIG. 1 is a functional block diagram of animage processing device 1 according toclaim 1. -
FIG. 2A illustrates an example of an image which anacquisition unit 2 acquires.FIG. 2B illustrates an example of a flesh-colored area which anextraction unit 3 extracts from the image.FIG. 2C illustrates an example of a group of candidate areas for a first region and second region which theextraction unit 3 extracts based on differences between pixel values of adjacent pixels in the flesh-colored area. -
FIG. 3 illustrates an example of a candidate area corresponding to the first region which adetection unit 4 detects. -
FIG. 4 illustrates an example of a connection direction which adetermination unit 5 determines. -
FIG. 5A is a diagram illustrating the candidate area corresponding to the first region and the connection direction thereof and a group of candidate areas for the second region.FIG. 5B is a diagram illustrating the candidate area corresponding to the first region detected by thedetection unit 4 and the candidate areas corresponding to the second region selected by aselection unit 6. -
FIG. 6 is a flowchart of the image processing carried out by theimage processing device 1. -
FIG. 7 is a hardware configuration diagram of theimage processing device 1 according toclaim 1. - Hereinafter, examples of an image processing device and image processing method according to
claims -
FIG. 1 is a functional block diagram of animage processing device 1 according to an embodiment. Theimage processing device 1 includes anacquisition unit 2,extraction unit 3,detection unit 4,determination unit 5, andselection unit 6. Theimage processing device 1 also includes a not-illustrated communication unit, and may use network resources by transmitting and receiving data bi-directionally to and from various external devices via a communication channel. - The
acquisition unit 2, for example, is a hardware circuit configured with a wired logic. Theacquisition unit 2 may also be a function module implemented by a computer program executed on theimage processing device 1. Theacquisition unit 2 receives an image imaged by an external device. The external device imaging the image is, for example, an image sensor. The image sensor is, for example, an imaging device such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) camera. When the image received from the image sensor is an analog image, theacquisition unit 2 may convert the analog image into a digital image through sampling, by which analog signals are extracted at discrete positions, and then quantization, by which the analog signals are converted to numerical values with finite resolution. Theacquisition unit 2 may also acquire the image by, for example, issuing instructions of imaging with an interval of 30 fps to the image sensor. The image sensor may be used as a head mounted camera (HMC). The image sensor, for example, images an image including a first region and second region of a user. The image sensor may also be included in theimage processing device 1 as appropriate. The first example will be described, for the purpose of illustration, on the assumption that the first region is a region including the dorsum of hand (may be referred to as the back of the hand) and a portion from the second joint to the third joint of a finger, and the second region is a region located in the direction from the second joint to the fingertip of a finger. If the second region is expressed in other words, regions located in the direction from the second joint to the fingertip of a finger include, for example, a region from the fingertip to the second joint, a region from the first joint to the second joint, and a region from the fingertip to the first joint. The first example will also be described, for the purpose of illustration, on the assumption that the dorsum of hand and a finger are in a state of facing the image sensor (in other words, in a state of being opposite to the image sensor), and, a finger (for example, index finger) is in a state of being spread to carry out interaction operation. Theacquisition unit 2 outputs the acquired image to theextraction unit 3. - The
extraction unit 3, for example, is a hardware circuit configured with a wired logic. Theextraction unit 3 may also be a function module implemented by a computer program executed on theimage processing device 1. Theextraction unit 3 receives the image from theacquisition unit 2. Theextraction unit 3 may, from the viewpoint of processing load reduction, distinguish flesh-colored areas from non-flesh-colored areas in the image, and exclude the non-flesh-colored areas from a series of image processing targets. The first example, for the purpose of illustration, will be described on the assumption that theextraction unit 3 distinguishes flesh-colored areas from non-flesh-colored areas in the image, and excludes the non-flesh-colored areas from a series of image processing targets. A flesh-colored area may be determined on any color space such as RGB, HSV, and YCbCr. For example, when the RGB color space is used, the methods to distinguish a flesh-colored area include a method to determine a flesh-colored area based on whether or not the pixel value of each color component of RGB (may be referred to as color feature quantity) is within an arbitrary range (for example, 100<R<255, 0<G<70, and 0<B<70), a method to determine a flesh-colored area by every pixel value (for example, when pixel values are (R1, G1, B1), the pixel is decided to be in a flesh-colored area, and, when pixel values are (R2, G2, B2), the pixel is decided to be in a non-flesh-colored area), and so on. The RGB, HSV, and YCbCr color spaces may be interconverted with one another, and it thus becomes possible to determine a flesh-colored area on other color spaces in the same manner as on the above-described RGB color space. - The
extraction unit 3 receives the image from theacquisition unit 2 and extracts a group of candidate areas for the first region and second region of a user included in the image based on pixel values in the image. In other words, theextraction unit 3, for example, extracts a group of candidate areas based on a predetermined first pixel value which is determined based on differences between pixel values of adjacent pixels in the image and by which the first region and second region are extracted separately. Specifically, theextraction unit 3 separates pixels included in the flesh-colored area into a plurality of areas (a group of candidate areas for the first region and second region). Theextraction unit 3 may, for example, extract a group of candidate areas by using differences between pixel values of adjacent pixels in the flesh-colored area. When it is assumed that (Ra, Ga, Ba) and (Rb, Gb, Bb) denote pixel values of adjacent pixels A and B, respectively, a difference between the pixel values (may be referred to as distance) D_ab may be expressed by the following formula. - The
extraction unit 3, when the difference between pixel values D_ab is less than a predetermined first pixel value (for example, a first pixel value of 5) in the above (formula 1), extracts the areas as candidate areas in an identical group, and, when the difference between pixel values D_ab is equal to or greater than the threshold value, extracts the areas as candidate areas in different groups. -
FIG. 2A illustrates an example of an image which theacquisition unit 2 acquires.FIG. 2B illustrates an example of a flesh-colored area which theextraction unit 3 extracts from the image.FIG. 2C illustrates an example of a group of candidate areas for the first region and second region which theextraction unit 3 extracts based on differences between pixel values of adjacent pixels in the flesh-colored area. InFIG. 2A , the image which theacquisition unit 2 acquires includes the first region and second region of a user which overlap a plane of paper including information such as a photograph and the flesh-colored background. As illustrated inFIG. 2A , the dorsum of hand and a finger (index finger) of the user are in a state of facing the image sensor, and, the finger is in a state of being spread straight to carry out interaction operation. As illustrated inFIG. 2B , theextraction unit 3 may, by using the method disclosed above, extract the flesh-colored area included in the image. InFIG. 2B , the first region and second region of the user and the background area of the plane of paper are extracted as a flesh-colored area. Theextraction unit 3, by using the method disclosed above, extracts the group of candidate areas for the first region and second region from the flesh-colored area based on differences between pixel values of adjacent pixels. InFIG. 2C , the first region is extracted as a candidate area in a group, and the second region is extracted as a plurality of candidate areas in a state of being separated into a plurality of groups. The background area of the plane of paper is also extracted as candidate areas in a state of being separated into a plurality of groups. This is because pixel values of the plane of paper, for example, vary under the influence of surface reflection of light. - A condition which determines the first pixel value based on differences between pixel values of adjacent pixels will be described below. The first pixel value may be any pixel value by which the first region, second region, and background area are extracted separately. The idea of the first pixel value is an idea which is newly revealed through consistent study by the applicants and has not been previously disclosed. In an image including the dorsum of hand and a finger, because regions including wrinkles of skin existing on the first joint and second joint of a finger or nails have complex shapes, differences between pixel values of adjacent pixels have pixel values peculiar to the regions.
- On the other hand, because the dorsum of hand and the region including a portion from the second joint to the third joint of a finger carrying out interaction operation do not have substantially peculiar shapes, there is little difference between pixel values of adjacent pixels. Hence, the
extraction unit 3 may determine a predetermined second pixel value (for example, a second pixel value of 7), which makes it possible to separate the first region from the second region, in advance. Boundary portions between the first region and second region and the background area have differences between pixel values of adjacent pixels, which are peculiar to the boundary regions, due to influence of shade of light even when the background area is a flesh-colored area. Therefore, theextraction unit 3 may determine a predetermined third pixel value (for example, a third pixel value of 5), which makes it possible to separate the first region and second region from the background area, in advance. In this processing, the first pixel value may be determined by a process in which the second pixel value and the third pixel value are compared, and the smaller one (the value which makes it possible both to separate the first region from the second region and to separate the first region and second region from the background area) is determined as the first pixel value. By using the first pixel value, theextraction unit 3 may extract a group of candidate areas for the first region and second region from the areas corresponding to the first region and second region and the area other than the areas corresponding to the first region and second region (background area). - The
extraction unit 3 may extract the group of candidate areas for the first region and second region based on, for example, an edge extraction method disclosed in "N. Senthilkumaran et al., Edge Detection Techniques for Image Segmentation, A Survey of Soft Computing Approaches, International Journal of Recent Trends in Engineering, Vol. 1, No. 2, May 2009". Theextraction unit 3 outputs the extracted group of candidate areas to thedetection unit 4 andselection unit 6. - The
detection unit 4 illustrated inFIG. 1 is, for example, a hardware circuit configured with a wired logic. Thedetection unit 4 may also be a function module implemented by a computer program executed on theimage processing device 1. Thedetection unit 4 receives the group of candidate areas from theextraction unit 3. Thedetection unit 4 detects a candidate area corresponding to the first region from the group of candidate areas based on biometric characteristics of the first region. The biometric characteristics, for example, may include at least one of the area, shape, and statistic of pixel values of the first region. Thedetection unit 4 outputs the detected candidate area for the first region to thedetermination unit 5. Details of detection processing in thedetection unit 4 with respect to each biometric characteristic of the first region will be described below. Thedetection unit 4, however, may detect a candidate area corresponding to the first region by combining individual biometric characteristics in order to improve robustness. - (Method to detect the candidate area corresponding to the first region based on the area of the first region)
- The
detection unit 4 detects the candidate area corresponding to the first region based on the area of the first region, which is an example of biometric characteristics. When the area of each candidate area in the group of candidate areas received from theextraction unit 3 is denoted by Sn (the unit may, for example, be the number of pixels), thedetection unit 4 may detect the candidate area corresponding to the first region based on the following formula. - In the above (formula 2), however, TH01 and TH02 denote arbitrary threshold values, which may be determined by measuring in advance a typical first region of a single user or a plurality of users who use(s) the
image processing device 1. For example, when it is assumed that the size of an image theacquisition unit 2 acquires is 76800 pixels (320 pixels × 240 pixels), and the distance between the image sensor and the first region is 50 cm, TH01 and TH02 may be determined to have values of 2000 pixels and 10000 pixels, respectively. When thedetection unit 4 detects a plurality of candidate areas corresponding to the first region which satisfy the condition expressed by the above (formula 2), for example, thedetection unit 4 may detect a candidate area that has the area value closest to the mean value of TH01 and TH02 as the candidate area corresponding to the first region. - The
detection unit 4 detects a candidate area corresponding to the first region based on the shape of the first region, which is an example of biometric characteristics. Thedetection unit 4 may detect the candidate area corresponding to the first region by carrying out any type of template matching between the outer edges of each candidate area in the group of candidate areas and, for example, the outer edges of a pre-measured first region(s) of a single user or a plurality of users. Thedetection unit 4 may also detect the candidate area corresponding to the first region by detecting parallel line segments of the outer edges of candidate areas in the group of candidate areas (because the width of a finger is substantially invariable, the outer edges at the left end and the right end of the finger constitute parallel line segments) and selecting a candidate area the detected parallel line segments of which are shorter than or equal to a predetermined threshold value (the threshold value may be appropriately defined based on the length from the second joint to the third joint of a finger). Thedetection unit 4 may use, as the method to detect parallel line segments, a method disclosed in, for example, "Zheng et. al., A Parallel-Line Detection Algorithm Based on HMM Decoding, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 5, MAY 2005" or "Song et. al., A Hough transform based line recognition method utilizing both parameter space and image space, Pattern Recognition, 38, 2005, p.539 - p.552". When thedetection unit 4 detects a plurality of candidate areas corresponding to the first region which satisfy the above-described condition, for example, thedetection unit 4 may detect a candidate area which has a highest degree of similarity to the template or a candidate area the parallel line segment length of which is closest to the predetermined threshold value as the candidate area corresponding to the first region. - The
detection unit 4 detects the candidate area corresponding to the first region based on a statistic of pixel values of the first region, which is an example of biometric characteristics. Thedetection unit 4 may detect the candidate area corresponding to the first region by using the average pixel value (Ar, Ag, Ab) and standard deviation (σr, σg, σb) (for example, on the RGB color space) of each candidate area in the group of candidate areas received from theextraction unit 3, based on the following formulae. - In the above (formulae 3), TH03 to TH14 denote arbitrary threshold values which may be determined by measuring a typical first region of a single user or a plurality of users who use(s) the
image processing device 1, in advance. For example, each threshold value may be determined as: TH03=170; TH04=200; TH05=60; TH06=120; TH07=110; TH08=160; TH09=5; TH10=15; TH11=10; TH12=30; TH=13; and TH14=30. - A technical reason for which the
detection unit 4 may detect the candidate area corresponding to the first region based on a statistic of pixel values, which is an example of biometric characteristics, will be described below. The dorsum of hand and the area from the second joint to the third joint include minuscule portions with slightly different colors (may be referred to as color characteristic quantity), such as a slightly reddish portion, a slightly whitish portion, and a slightly blackish portion (above a blood vessel or the like). Hence, the standard deviation of pixel values in the dorsum of hand and the area from the second joint to the third joint is larger than those on the plane of paper with a single color of the flesh color, which is an example of the background. It is possible for thedetection unit 4 to use variance in place of standard deviation. When thedetection unit 4 detects a plurality of candidate areas corresponding to the first region which satisfy the conditions expressed by the above (formulae 3), for example, thedetection unit 4 may detect a candidate area the average pixel value of which is closest to the mean value of TH03 and TH04 or TH09 and TH10 as the candidate area corresponding to the first region. -
FIG. 3 illustrates an example of the candidate area corresponding to the first region which thedetection unit 4 detects. As illustrated inFIG. 3 , thedetection unit 4 detects the candidate area corresponding to the first region from the group of candidate areas illustrated inFIG. 2C based on biometric characteristics of the first region. Thedetection unit 4 outputs the detected candidate area corresponding to the first region to thedetermination unit 5. - The
determination unit 5 illustrated inFIG. 1 is, for example, a hardware circuit configured with a wired logic. Thedetermination unit 5 may be a function module implemented by a computer program executed on theimage processing device 1. Thedetermination unit 5 receives, from thedetection unit 4, the candidate area corresponding to the first region detected by thedetection unit 4. Thedetermination unit 5 determines a connection direction between the first region and the second region based on the outer edges of the candidate area for the first region. - First, the
determination unit 5 detects outer edges from the candidate area corresponding to the first region. Thedetermination unit 5 may use various well-known methods as a method to detect outer edges. Thedetermination unit 5 may use, as a method to detect outer edges, a method disclosed in, for example, "Song et. al., A Hough transform based line recognition method utilizing both parameter space and image space, Pattern Recognition, 38, 2005, p.539 - p.552". Next, thedetermination unit 5 detects parallel line segments from the detected outer edges. The parallel line segments, for example, correspond to the outer edges of the portion from the second joint to the third joint of the finger (because the width of a finger is substantially invariable, the outer edges at the left end and right end of the finger constitute parallel line segments). Thedetermination unit 5 may use, as a method to detect parallel line segments, a method disclosed in, for example, "Zheng et. al., A Parallel-Line Detection Algorithm Based on HMM Decoding, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 5, MAY 2005" or "Niinuma et. al., Detecting Shading Regions based on the Contour Representation of an Image, The Special Interest Group Technical Reports of IPSJ, 2001, 36, p1-8". Although the width of a finger is substantially invariable, the outer edges of the finger are not parallel in a precise sense. As a result, thedetermination unit 5 may use any threshold decision method in detection of parallel line segments. The threshold value may be determined by measuring an angle made by the outer edges at the left end and right end of a typical finger of a single user or a plurality of users who use(s) theimage processing device 1. For example, thedetermination unit 5 may decide that two line segments are parallel line segments if the angle made by the two line segments is less than 5°. In this case, thedetermination unit 5 may define completely parallel line segments by correcting the gradient of each of two line segments decided to be parallel with, for example, the quotient of the angle made by the two line segments divided by 2. When thedetermination unit 5 detects a plurality of parallel line segments (in other words, when parallel line segments of portions from the second joints to the third joints of the thumb and the index finger are detected), for example, thedetermination unit 5 may regard the longest parallel line segments as the finger by which the user is carrying out interactive operation. -
FIG. 4 illustrates an example of a connection direction which thedetermination unit 5 determines. As illustrated inFIG. 4 , thedetermination unit 5 determines parallel line segments from the outer edges and further determines the connection direction from the parallel line segments. It is sufficient for the connection direction to be, for example, parallel with the parallel line segments. When, for example, the upper left corner of the image acquired by theacquisition unit 2 is the origin, the horizontal direction is denoted by x, and the vertical direction is denoted by y, thedetermination unit 5 may determine information expressed by y=ax+b (a and b are arbitrary coefficients) as the connection direction. The information may be referred to as an extension line of the median line of the parallel line segments. Thedetermination unit 5 outputs the determined connection direction between the first region and second region to theselection unit 6. - The
selection unit 6 illustrated inFIG. 1 , for example, is a hardware circuit configured with a wired logic. Theselection unit 6 may be a function module implemented by a computer program executed on theimage processing device 1. Theselection unit 6 receives the connection direction from thedetermination unit 5 and the group of candidate areas from theextraction unit 3. Theselection unit 6 selects candidate areas corresponding to the second region based on the connection direction from the group of candidate areas excluding the candidate area corresponding to the first region. Theselection unit 6, for example, selects candidate areas corresponding to the second region based on distances between the extension line of the median line of the parallel line segments and outer edges of the group of candidate areas or areas between extension lines of the parallel line segments. Furthermore, theselection unit 6, for example, selects candidate areas corresponding to the second region further based on the areas of the group of candidate areas or pixel values of the first region and the group of candidate areas. Details of the selection processing by theselection unit 6 will be described below. Theselection unit 6 may, however, detect candidate areas corresponding to the second region by combining selection processing methods in order to improve robustness. -
FIG. 5A is a diagram illustrating the candidate area corresponding to the first region and the connection direction thereof and a group of candidate areas for the second region.FIG. 5B is a diagram illustrating the candidate area corresponding to the first region detected by thedetection unit 4 and the candidate areas corresponding to the second region selected by theselection unit 6. InFIG. 5A , the connection direction between the first region and the second region (may be referred to as an extension line of the median line of parallel line segments), the parallel line segments, and extension lines of the parallel line segments are illustrated. Theselection unit 6, for example, selects candidate areas existing in the connection direction as candidate areas corresponding to the second region. Theselection unit 6, for example, may also select candidate areas corresponding to the second region based on areas between the extension lines of the parallel line segments. This selection processing uses a biometric characteristic in that outer edges of regions from the fingertip to the first joint to the second joint to the third joint (outer edges of a finger) constitute substantially straight lines. - The
selection unit 6 illustrated inFIG. 1 may select candidate areas corresponding to the second region based on, for example, a distance B_distance (the unit may, for example, be the number of pixels) between extension lines of the parallel line segments and outer edges of the group of candidate areas (for example, distance between the extension line of the median line of the parallel line segments and a point on the outer edges that is furthest from the extension line of the median line of the parallel line segments). Theselection unit 6 may, for example, select candidate areas that satisfy a condition expressed by the following formula as the candidate areas corresponding to the second region. - In the above (formula 4), TH15 is an arbitrary threshold value which is determined by measuring in advance a typical second region of a single user or a plurality of users who use(s) the
image processing device 1. For example, TH15 may be 10. By applying the above (formula 4), it becomes possible to avoid selecting, as a candidate area corresponding to the second region, a candidate area with an oblong shape which does not correspond to a finger shape from among candidate areas existing on the extension line of the median line of the parallel line segments. - The
selection unit 6 may, for example, select candidate areas corresponding to the second region based on an area B_area (the unit may, for example, be the number of pixels) of a candidate area in the group of candidate areas. Theselection unit 6 may, for example, select a candidate area that satisfies a condition expressed by the following formula as a candidate area corresponding to the second region. - In the above (formula 5), TH16 and TH17 are arbitrary threshold values which are determined by measuring in advance a typical second region of a single user or a plurality of users who use(s) the
image processing device 1. For example, TH16 and TH17 may be 2 and 300, respectively. By applying the above (formula 5), it becomes possible to avoid selecting, as a candidate area corresponding to the second region, a candidate area with too large area or a candidate area with too small area to correspond to a finger shape from among candidate areas existing on the extension line of the median line of the parallel line segments. TH16 may be determined based on the area of minuscule areas produced by shade of light. - The
selection unit 6 may, for example, select a candidate area corresponding to the second region based on an average value B_ave and standard deviation β_σ of pixel values of each candidate area in the group of candidate areas and an average value A_ave and standard deviation A_σ of pixel values of the candidate area corresponding to the first region. Theselection unit 6 may, for example, select a candidate area that satisfies a condition expressed by the following formula as a candidate area corresponding to the second region. - In the above (formula 6), TH18 and TH19 are arbitrary threshold values which are determined by measuring a typical first region and second region of a single user or a plurality of users who use(s) the
image processing device 1 in advance. For example, TH18 and TH19 may be 20 and 5, respectively. TH18 and TH19 may be determined based on a biometric characteristic in that pigments of adjacent skin areas resemble each other. - As illustrated in
FIG. 5B , the image processing device 1 (for example, the selection unit 6) may regard a concatenation of the candidate area corresponding to the first region detected by thedetection unit 4 and the candidate areas corresponding to the second region selected by theselection unit 6 as a finger of the user, and detect a position of the fingertip from the outer edge (contour) of the finger by an arbitrary method. Theimage processing device 1 may use, as a method to detect a position of the fingertip, a method disclosed in, for example, "Survey on Skin Tone Detection using Color Spaces, C. Prema et al., International Journal of Applied Information Systems 2(2): 18-26, May 2012. Published by Foundation of Computer Science, New York, USA.". Theimage processing device 1 outputs the detected position of the fingertip to an external device (for example, an information processing terminal device or the like). - The
image processing device 1 may, for example, be configured with integrated circuits such as an application specific integrated circuit (ASIC) and field programmable gate array (FPGA). -
FIG. 6 is a flowchart of the image processing carried out by theimage processing device 1. Theacquisition unit 2, for example, receives, from the image sensor, an image imaged by the image sensor which includes at least the first region and second region of a user (step S601). In step S601, when the image received from the image sensor is an analog image, theacquisition unit 2 may convert the analog image into a digital image through sampling, by which analog signals are extracted at discrete positions, and then quantization, by which the analog signals are converted to numerical values with finite resolution. Theacquisition unit 2 may also acquire the image by, for example, issuing instructions of imaging with an interval of 30 fps to the image sensor. The following description will be done on the assumption that the first region is a region including the dorsum of hand (may be referred to as the back of the hand) and a portion from the second joint to the third joint of a finger, and the second region is a region located in the direction from the second joint to the fingertip of the finger. The description will also be done, for the purpose of illustration, on the assumption that the dorsum of hand and the finger are in a state of facing the image sensor (in other words, in a state of being opposite to the image sensor), and, a finger (for example, index finger) is in a state of being spread to carry out interaction operation. Theacquisition unit 2 outputs the acquired image to theextraction unit 3. - The
extraction unit 3 receives the image from theacquisition unit 2, and extracts a group of candidate areas for the first region and second region of the user included in the image based on pixel values in the image (step S602). In other words, theextraction unit 3, for example, extracts a group of candidate areas based on a predetermined first pixel value which is determined based on differences between pixel values of adjacent pixels in the image and by which the first region and the second region are extracted separately. Specifically, theextraction unit 3 separates pixels included in a flesh-colored area into a plurality of areas (a group of candidate areas for the first region and second region). Theextraction unit 3, for example, extracts the group of candidate areas by using differences between pixel values of adjacent pixels in the flesh-colored area and the above-described processing method of theextraction unit 3. Though not illustrated, when, in step S602, no group of candidate areas is extracted, theacquisition unit 2 may acquire an image at a different moment (for example, the next frame) (step S601), and theextraction unit 3 may carry out the processing in step S602 again. - Furthermore, in step S602, the
extraction unit 3 may, from the viewpoint of processing load reduction, distinguish flesh-colored areas from non-flesh-colored areas in the image by using the above-described processing method of theextraction unit 3, and exclude the non-flesh-colored areas from a series of image processing targets. In the description of the flowchart illustrated inFIG. 6 , for the purpose of illustration, it is assumed that theextraction unit 3 distinguishes the flesh-colored area from the non-flesh-colored areas in the image and excludes the non-flesh-colored areas from a series of image processing targets. Theextraction unit 3 outputs the extracted group of candidate areas to thedetection unit 4 andselection unit 6. - The
detection unit 4 receives the group of candidate areas from theextraction unit 3. Thedetection unit 4, by using the above-described processing method of thedetection unit 4, detects the candidate area corresponding to the first region from the group of candidate areas based on biometric characteristics of the first region (step S603). The biometric characteristics may, for example, include at least one of the area, the shape, and a statistic of pixel values of the first region. Thedetection unit 4 outputs the detected candidate area for the first region to thedetermination unit 5. - The
determination unit 5 receives, from thedetection unit 4, the candidate area corresponding to the first region detected by thedetection unit 4. Thedetermination unit 5, based on the outer edges of the candidate area for the first region, determines the connection direction between the first region and the second region by using the above-described processing method of the determination unit 5 (S604). In step S602, when thedetermination unit 5 detects a plurality of parallel line segments (in other words, when parallel line segments of portions from the second joints to the third joints of the thumb and the index finger are detected), for example, thedetermination unit 5 may regard the longest parallel line segments as the finger by which the user is carrying out interactive operation. Thedetermination unit 5 outputs the determined connection direction between the first region and the second region to theselection unit 6. - The
selection unit 6 receives the connection direction from thedetermination unit 5 and the group of candidate areas from theextraction unit 3. Theselection unit 6, based on the connection direction, selects candidate areas corresponding to the second region from the group of candidate areas excluding the candidate area corresponding to the first region by using the above-described processing method of the selection unit 6 (step S605). Theselection unit 6, for example, selects candidate areas corresponding to the second region based on distances between the extension line of the median line of the parallel line segments and the outer edges of the group of candidate areas or areas between extension lines of the parallel line segments. Furthermore, theselection unit 6, for example, selects candidate areas corresponding to the second region further based on the area of the group of candidate areas or pixel values of the first region and the group of candidate areas. In step S605, theselection unit 6 may, in order to improve robustness, detect a candidate area corresponding to the second region by combining the above-described selection processing methods. - The image processing device 1 (for example, the selection unit 6) regards a concatenation of the candidate area corresponding to the first region detected by the
detection unit 4 and the candidate areas corresponding to the second region selected by theselection unit 6 as a finger of the user, and detects a position of the fingertip from the outer edge (contour) of the finger by an arbitrary method (step S606). With this processing, theimage processing device 1 ends the image processing illustrated in the flowchart ofFIG. 6 . - With the image processing device of the example 1, it becomes possible to locate a position of a finger of a user accurately without being influenced by a background color. Although a case in which a hand is flesh-colored, the background is also flesh-colored, and the processing methods for these portions are similar has been described as an example in the example 1, embodiments are not limited to this case. For example, it will be appreciated that the embodiment described in the example 1 is also applicable to a case in which fingers are covered by a glove and a background with a similar color to the color of the glove is used.
-
FIG. 7 is a hardware configuration diagram of a computer which functions as animage processing device 1 according to an embodiment. As illustrated inFIG. 7 , theimage processing device 1 is configured with acomputer 100 and input/output devices (peripheral devices) connected to thecomputer 100. - The
whole computer 100 is controlled by aprocessor 101. To theprocessor 101, a random access memory (RAM) 102 and a plurality of peripheral devices are connected via abus 109. Theprocessor 101 may be a multiprocessor. Theprocessor 101 is, for example, a CPU, micro processing unit (MPU), digital signal processor (DSP), application specific integrated circuit (ASIC), or programmable logic device (PLD). Moreover, theprocessor 101 may be a combination of two or more components among a CPU, MPU, DSP, ASIC, and PLD. Theprocessor 101 may, for example, carry out processing of function blocks such as anacquisition unit 2,extraction unit 3,detection unit 4,determination unit 5, andselection unit 6 inFIG. 1 . - The
RAM 102 is used as a main memory of thecomputer 100. To theRAM 102, at least a portion of operating system (OS) programs and application programs, which are executed by theprocessor 101, are stored temporarily. To theRAM 102, various kinds of data, which is used in processing executed by theprocessor 101, are also stored. - Peripheral devices connected to the
bus 109 include a hard disk drive (HDD) 103, graphic processor unit 104,input interface 105,optical drive unit 106,device connection interface 107, andnetwork interface 108. - The HDD 103 carries out data writing and reading magnetically to and from an internal disk. The HDD 103, for example, is used as an auxiliary storage device for the
computer 100. To the HDD 103, OS programs, application programs, and various kinds of data are stored. Semiconductor memory devices such as a flash memory may also be used as an auxiliary storage device. - To the graphic processing device 104, a
monitor 110 is connected. The graphic processing device 104, following instructions from theprocessor 101, makes themonitor 110 display various images on a display thereof. A display device using a cathode ray tube (CRT) and a liquid crystal display device may be used for themonitor 110. - To the
input interface 105, akeyboard 111 and amouse 112 are connected. Theinput interface 105 transmits signals transmitted from thekeyboard 111 andmouse 112 to theprocessor 101. Themouse 112 is just an example of a pointing device. Other types of pointing devices may be used. The other types of pointing devices include a touch panel, tablet, touch pad, trackball and the like. - The
optical drive unit 106 reads out data recorded in theoptical disk 113 by using a laser beam or the like. Theoptical disk 113 is a portable recording medium on which data are recorded so as to be readable by the reflection of light. Theoptical disk 113 includes a digital versatile disc (DVD), DVD-RAM, compact disc read only memory (CD-ROM), compact disc-recordable (CD-R), compact disc-rewritable (CD-RW), or the like. Programs stored in theoptical disk 113, which is a portable recording medium, are installed in theimage processing device 1 via theoptical drive unit 106. The installed pre-arranged programs become executable on theimage processing device 1. - The
device connection interface 107 is a communication interface to connect peripheral devices to thecomputer 100. For example, to thedevice connection interface 107, amemory device 114, memory reader/writer 115, andimage sensor 118 may be connected. The memory device is a recording medium equipped with a communication function with thedevice connection interface 107. The memory reader/writer 115 is a device configured to write data to amemory card 116, or to read out data from thememory card 116. Thememory card 116 is a card-type recording medium. Theimage sensor 118 is, for example, an imaging device such as a charge coupled device (CCD) and complementary metal oxide semiconductor (CMOS) camera. Theimage sensor 118, for example, images an image including the first region and second region of a user. - The
network interface 108 is connected to anetwork 117. Thenetwork interface 108 transmits and receives data to and from another computer or communication device via thenetwork 117. - The
computer 100, for example, accomplishes the above-described image processing function by executing programs recorded in a computer-readable recording medium. The programs describing processing details executed by thecomputer 100 may be recorded in various recording media. The above-described programs may be configured with one or a plurality of function modules. For example, the programs may be configured with function modules that accomplish the processing of theacquisition unit 2,extraction unit 3,detection unit 4,determination unit 5, andselection unit 6 illustrated inFIG. 1 . The programs executed by thecomputer 100 may be stored in the HDD 103. Theprocessor 101 loads at least a portion of the programs stored in the HDD 103 into theRAM 102 and executes the programs. The programs executed by thecomputer 100 may also be recorded in a portable recording medium such as theoptical disk 113,memory device 114, andmemory card 116. The programs stored in a portable recording medium, for example, are installed in the HDD 103 under the control of theprocessor 101, and then become executable. Theprocessor 101 may directly read out the programs from the portable recording medium and execute the programs. - Individual components of the illustrated units do not have to be physically configured as illustrated. In other words, specific manner of configuration of the individual units such as distributed configuration or integrated configuration is not limited to the illustrated ones, and the whole or part of the components may be functionally or physically configured in a distributed manner or integrated manner in any unit in accordance with various levels of load and usage conditions. The various types of processing described in the above examples may be implemented by executing pre-arranged programs on a computer such as a personal computer and workstation.
Claims (9)
- An image processing device (1) which includes a computer processor, the image processing device comprising:an acquisition unit (2) configured to acquire an image which includes a first region and a second region of a user, the first region consisting of a dorsum of a hand and a portion from a second joint to a third joint of a finger of the hand, and the second region consisting of a region from the fingertip to the second joint of the finger of the hand;an extraction unit (3) configured to extract the plurality of candidate areas based on a predetermined first pixel value, the predetermined first pixel value being determined in advance based on differences between pixel values of adjacent pixels in regions including wrinkles of skin existing on the first joint and second joint of a finger and differences between pixel values of adjacent pixels in boundary portions between first region and second region and background area;a detection unit (4) configured to detect, from a plurality of candidate areas for the first region and the second region included in the image, a first candidate area corresponding to the first region based on a predetermined image feature of the first region, wherein the predetermined image feature includes at least one of an area of the first region, a shape of the first region, mean of the pixel values of the first region, and variance of the pixel values of the first region, determined in advance by measuring a typical first region;a determination unit (5) configured to determine parallel lines included in outer edges of the first candidate area; anda selection unit (6) configured to select a second candidate area corresponding to the second region from the plurality of candidate areas based on the parallel lines.
- The device according to claim 1, further comprising
an extraction unit (3) is configured to extract the plurality of candidate areas based on a predetermined first pixel value, the predetermined first pixel value being determined based on image feature of regions including wrinkles of skin existing on the first joint and second joint of a finger or regions including wrinkles of skin existing on the first joint and second joint of a finger or regions including nails. - The device according to claim 1, wherein the determination unit (5) is configured to determine the connection direction based on parallel line segments of the outer edges which are determined from the outer edges.
- The device according to claim 3, wherein the selection unit (6) is configured to select the candidate area corresponding to the second region based on a distance between an extension line of a median line of the parallel line segments and outer edges of the group of candidate areas or an area between extension lines of the parallel line segments.
- The device according to claim 3,
wherein the selection unit (6) is configured to select the second candidate area further based on an area of the plurality of candidate areas or pixel values of the first region and the plurality of candidate areas. - An image processing method comprising:acquiring (S601) an image which includes a first region and a second region of a user, the first region consisting of a dorsum of a hand and a portion from a second joint to a third joint of a finger of the hand, and the second region consisting of a region from the fingertip to the second joint of the finger of the hand;extracting the plurality of candidate areas based on a predetermined first pixel value, the predetermined first pixel value being determined in advance based on differences between pixel values of adjacent pixels in regions including wrinkles of skin existing on the first joint and second joint of a finger and differences between pixel values of adjacent pixels in boundary portions between first region and second region and background area;detecting (S603), from a plurality of candidate areas for the first region and the second region included in the image, a first candidate area corresponding to the first region based on a predetermined image feature of the first region, wherein the predetermined image feature includes at least one of an area of the first region, a shape of the first region, mean of the pixel values of the first region, and variance of the pixel values of the first region, determined in advance by measuring a typical first region;determining (S604) parallel lines included in outer edges of the first candidate area; andselecting (S605) a second candidate area corresponding to the second region from the plurality of candidate areas based on the parallel lines.
- The method according to claim 6, further comprising extracting the plurality of candidate areas based on a predetermined first pixel value, the predetermined first pixel value being determined based on image feature of regions including wrinkles of skin existing on the first joint and second joint of a finger or regions including wrinkles of skin existing on the first joint and second joint of a finger or regions including nails.
- The method according to claim 6, wherein the determining includes determining the connection direction based on parallel line segments of the outer edges which are determined from the outer edges.
- The method according to claim 8, wherein the selecting includes selecting the candidate area corresponding to the second region based on a distance between an extension line of a median line of the parallel line segments or an area between extension lines of the parallel line segments.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014026020A JP6326847B2 (en) | 2014-02-14 | 2014-02-14 | Image processing apparatus, image processing method, and image processing program |
Publications (2)
Publication Number | Publication Date |
---|---|
EP2908267A1 EP2908267A1 (en) | 2015-08-19 |
EP2908267B1 true EP2908267B1 (en) | 2018-12-12 |
Family
ID=52015946
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP14196764.6A Not-in-force EP2908267B1 (en) | 2014-02-14 | 2014-12-08 | Image processing device and image processing method |
Country Status (3)
Country | Link |
---|---|
US (1) | US9870059B2 (en) |
EP (1) | EP2908267B1 (en) |
JP (1) | JP6326847B2 (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6335695B2 (en) * | 2014-07-09 | 2018-05-30 | キヤノン株式会社 | Information processing apparatus, control method therefor, program, and storage medium |
JP6478713B2 (en) * | 2015-03-04 | 2019-03-06 | キヤノン株式会社 | Measuring device and measuring method |
JP6464889B2 (en) | 2015-03-31 | 2019-02-06 | 富士通株式会社 | Image processing apparatus, image processing program, and image processing method |
JP6708218B2 (en) | 2015-12-16 | 2020-06-10 | 日本電気株式会社 | Information processing device, intrusion detection method, and computer program |
JP2017118229A (en) | 2015-12-22 | 2017-06-29 | ソニー株式会社 | Information processing device, information processing method, and program |
EP3846064A1 (en) * | 2019-12-30 | 2021-07-07 | Dassault Systèmes | Selection of a vertex with an immersive gesture in 3d modeling |
EP3846003A1 (en) | 2019-12-30 | 2021-07-07 | Dassault Systèmes | Selection of a face with an immersive gesture in 3d modeling |
EP3846004A1 (en) | 2019-12-30 | 2021-07-07 | Dassault Systèmes | Selection of an edge with an immersive gesture in 3d modeling |
CN114419074B (en) * | 2022-03-25 | 2022-07-12 | 青岛大学附属医院 | 4K medical image processing method |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3458543B2 (en) * | 1995-07-25 | 2003-10-20 | 株式会社日立製作所 | Information processing device with hand shape recognition function |
JPH09102046A (en) | 1995-08-01 | 1997-04-15 | Matsushita Electric Ind Co Ltd | Hand shape recognition method/device |
JP3863809B2 (en) | 2002-05-28 | 2006-12-27 | 独立行政法人科学技術振興機構 | Input system by hand image recognition |
JP2004348522A (en) * | 2003-05-23 | 2004-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Detection method of palm-shape authentication reference point, and palm-shape authentication reference point detection device, program, and recording medium |
JP2006163662A (en) | 2004-12-06 | 2006-06-22 | Nissan Motor Co Ltd | Device and method for recognizing number of fingers |
US7720281B2 (en) * | 2006-07-31 | 2010-05-18 | Mavs Lab, Inc. | Visual characteristics-based news anchorperson segment detection method |
US20130135199A1 (en) * | 2010-08-10 | 2013-05-30 | Pointgrab Ltd | System and method for user interaction with projected content |
US9135503B2 (en) | 2010-11-09 | 2015-09-15 | Qualcomm Incorporated | Fingertip tracking for touchless user interface |
WO2012139242A1 (en) * | 2011-04-11 | 2012-10-18 | Intel Corporation | Personalized program selection system and method |
JP5935308B2 (en) | 2011-12-13 | 2016-06-15 | 富士通株式会社 | User detection device, method and program |
JP6155786B2 (en) * | 2013-04-15 | 2017-07-05 | オムロン株式会社 | Gesture recognition device, gesture recognition method, electronic device, control program, and recording medium |
-
2014
- 2014-02-14 JP JP2014026020A patent/JP6326847B2/en not_active Expired - Fee Related
- 2014-12-03 US US14/559,014 patent/US9870059B2/en active Active
- 2014-12-08 EP EP14196764.6A patent/EP2908267B1/en not_active Not-in-force
Non-Patent Citations (1)
Title |
---|
None * |
Also Published As
Publication number | Publication date |
---|---|
US20150234471A1 (en) | 2015-08-20 |
EP2908267A1 (en) | 2015-08-19 |
US9870059B2 (en) | 2018-01-16 |
JP6326847B2 (en) | 2018-05-23 |
JP2015153120A (en) | 2015-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2908267B1 (en) | Image processing device and image processing method | |
US10699146B2 (en) | Mobile document detection and orientation based on reference object characteristics | |
US9710109B2 (en) | Image processing device and image processing method | |
US10216979B2 (en) | Image processing apparatus, image processing method, and storage medium to detect parts of an object | |
US9405182B2 (en) | Image processing device and image processing method | |
US20200293809A1 (en) | Image processing apparatus, image processing method, and storage medium | |
EP2980755B1 (en) | Method for partitioning area, and inspection device | |
US9483680B2 (en) | Method of recognizing contactless fingerprint and electronic device for performing the same | |
JP2000105829A (en) | Method and device for face parts image detection | |
US10402639B2 (en) | Identifying document forms using digital fingerprints | |
RU2581786C1 (en) | Determination of image transformations to increase quality of optical character recognition | |
RU2673015C1 (en) | Methods and systems of optical recognition of image series characters | |
US10395090B2 (en) | Symbol detection for desired image reconstruction | |
Verma et al. | Removal of obstacles in Devanagari script for efficient optical character recognition | |
KR20190059083A (en) | Apparatus and method for recognition marine situation based image division | |
JP5971108B2 (en) | Image processing apparatus, image processing method, and image processing program | |
Simha et al. | Recognition of numbers and position using image processing techniques for solving sudoku puzzles | |
Ghoshal et al. | An improved scene text and document image binarization scheme | |
CN105654082A (en) | Method and equipment for character identification post-processing and image picking equipment comprising equipment | |
JP2011087144A (en) | Telop character area detection method, telop character area detection device, and telop character area detection program | |
US10853972B2 (en) | Apparatus for processing image and method thereof | |
KR101200009B1 (en) | Presentation system for providing control function using user's hand gesture and method thereof | |
JP6467994B2 (en) | Image processing program, image processing apparatus, and image processing method | |
JP6273686B2 (en) | Image processing apparatus, image processing method, and image processing program | |
US10134163B2 (en) | Dynamic detection of an object framework in a mobile device captured image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
17P | Request for examination filed |
Effective date: 20160212 |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20170823 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Ref document number: 602014037773 Country of ref document: DE Free format text: PREVIOUS MAIN CLASS: G06K0009000000 Ipc: G06K0009460000 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06F 3/01 20060101ALI20180626BHEP Ipc: G06K 9/34 20060101ALI20180626BHEP Ipc: G06K 9/00 20060101ALI20180626BHEP Ipc: G06K 9/46 20060101AFI20180626BHEP Ipc: G06K 9/20 20060101ALI20180626BHEP |
|
INTG | Intention to grant announced |
Effective date: 20180718 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE PATENT HAS BEEN GRANTED |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 1076964 Country of ref document: AT Kind code of ref document: T Effective date: 20181215 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602014037773 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20190312 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20190312 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 1076964 Country of ref document: AT Kind code of ref document: T Effective date: 20181212 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20190313 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20190412 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20190412 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 602014037773 Country of ref document: DE |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
26N | No opposition filed |
Effective date: 20190913 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
REG | Reference to a national code |
Ref country code: BE Ref legal event code: MM Effective date: 20191231 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191208 Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191208 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191231 Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191231 Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191231 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20201126 Year of fee payment: 7 Ref country code: FR Payment date: 20201112 Year of fee payment: 7 Ref country code: DE Payment date: 20201124 Year of fee payment: 7 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20141208 Ref country code: MT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Ref document number: 602014037773 Country of ref document: DE Free format text: PREVIOUS MAIN CLASS: G06K0009460000 Ipc: G06V0030180000 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20181212 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 602014037773 Country of ref document: DE |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20211208 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20211208 Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220701 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20211231 |